Directly distill from Llama, the finetune in DPO
Junxiong Wang
JunxiongWang
AI & ML interests
Attention Free Model / Subquadratic Language Models
Organizations
Collections
7
models
45
JunxiongWang/Llama-3.2-1B-MATH
Text Generation
•
Updated
•
11
JunxiongWang/MambaInLlama1B_v4
Updated
•
6
JunxiongWang/MambaInLlama3B_v4
Updated
•
17
JunxiongWang/MambaInLlama3B_DPO2
Updated
•
19
JunxiongWang/MambaInLlama3B_DPO1
Updated
•
9
JunxiongWang/MambaInLlama3B_v3.1
Updated
•
189
JunxiongWang/MambaInLlama3B_v3
Updated
•
95
JunxiongWang/MambaInLlama1B_v3
Updated
•
114
JunxiongWang/mamba_0_5_distill
Updated
•
4
JunxiongWang/Llama3.2-Mamba-3B-dpo
Updated
•
26
datasets
11
JunxiongWang/test_math
Viewer
•
Updated
•
89.1k
•
129
JunxiongWang/FineMathV4
Viewer
•
Updated
•
6.7M
•
105
JunxiongWang/model_revision_max_4_closest_and_random
Viewer
•
Updated
•
530k
•
86
JunxiongWang/sftdatasetv4
Viewer
•
Updated
•
4.96M
•
87
JunxiongWang/sftdatasetv3
Viewer
•
Updated
•
12.4M
•
191
JunxiongWang/sftdatasetv2
Viewer
•
Updated
•
11.8M
•
73
JunxiongWang/sftdataset
Viewer
•
Updated
•
11M
•
479
•
2
JunxiongWang/llama3-ultrafeedback-armorm
Viewer
•
Updated
•
61.8k
•
143
•
1
JunxiongWang/gemma2_sftdataset
Viewer
•
Updated
•
11M
•
46
JunxiongWang/largetestdataset
Viewer
•
Updated
•
7.49M
•
34